© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170026
    Prev
    Next
    INDEX
    Explanations

    ไม่

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Much
    0.45
    much
    0.45
     much
    0.44
     Much
    0.42
     MUCH
    0.42
     гораздо
    0.38
    ᱞ
    0.35
     ngang
    0.35
    [][
    0.35
    కాం
    0.35
    POSITIVE LOGITS
     yet
    0.61
    Yet
    0.51
     Yet
    0.47
    quite
    0.47
     quite
    0.47
    yet
    0.46
     Quite
    0.46
    Quite
    0.42
     بسه
    0.39
     încă
    0.38
    Activations Density 0.000%

    No Known Activations